41results about How to "Efficient and accurate judgment" patented technology

The invention belongs to the field vehicle active safety, and particularly discloses a detection method and system, based on laser radar and binocular camera, for a pedestrian in front of vehicle. The method comprises the following steps: collection data of the front of the vehicle through the laser radar and the binocular camera; respectively processing the data collected by the laser radar and the binocular camera, so as to obtain the distance, azimuth angle and speed value of the pedestrian relative to the vehicle; correcting the information of the pedestrian through a Kalman filter. The method comprehensively utilizes a stereoscopic vision technology and a remote sensing technology, integrates laser radar and binocular camera information, is high in measurement accuracy and pedestrian detection accuracy, and can effectively reduce the occurrence rate of traffic accidents.

The invention discloses a mobile phone wearing mode-oriented falling event detection system and a mobile phone wearing mode-oriented falling event detection method. The system comprises an acceleration sensor installed on a mobile phone, and a data acquisition module, a falling pre-judgment module, a characteristic extraction module and a falling judgment module, which are sequentially connected with the data output end of the acceleration sensor. The method comprises the following steps that: firstly, the data acquisition module continuously acquires a wearer motion variation sensed by the acceleration sensor, squares components of three directions of acceleration, summates squares, extracts a sum, calculates a module of an acceleration vector, and simultaneously maintains a cache for recording historical acceleration information; secondly, the falling pre-judgment module periodically reads the data cache maintained by the data acquisition module, and judges whether falling possibly happens or not; thirdly, the characteristic extraction module acquires acceleration variation data a plurality of seconds before and after an event from the data acquisition module, and calculates characteristic components; and finally, the characteristic extraction module generates a characteristic vector by using the obtained characteristic components, and inputs the characteristic vector into the falling judgment module, and the falling judgment module which is obtained according to distinction motion training required by the use of the mobile phone judges whether the event belongs to a falling event or not.

The embodiment of the invention discloses a strabismus detection method based on a convolution neural network, which comprises the following steps: strabismus images are collected and a strabismus image database composed of strabismus images is established; A convolution neural network is trained to locate the eye region by using a common face database, and the learning parameters of the convolution neural network are determined. A convolutional neural network for slant-eye recognition is trained by using the oriental face data set OFD and slant-eye image database, and the learning parametersof the neural network are determined. The eye region of the strabismus image in the strabismus image library is located by using the trained convolution neural network for locating the eye region. thetrained convolution neural network is used for cross-eye recognition to recognize the cropped eye region image, the result of cross-eye detection is output. The invention fully utilizes the feature extraction and feature learning ability of the convolution neural network, can efficiently and accurately judge whether a person suffers from squint or not, and is helpful for doctors to diagnose and treat squint diseases.

The invention provides a physical condition evaluation device and a massage machine provided with the physical condition evaluation device. The massage machine (1) includes: a treatment piece control unit (41) for changing load applying status of a user; an organism physiological information measuring unit (32) for measuring reaction of an organism when the load is applied; an evaluation unit (42) for evaluating physical condition of the user according to the reaction of the organism. The treatment piece control unit (41) applies different loads to the user, the organism physiological information measuring unit (32) measures the reaction of the organism according to the different loads, and the evaluation unit (42) evaluates the physical condition according to the reaction of the organism corresponding to each load, so that the physical condition evaluation device can efficiently and accurately determine the physical condition.

The invention discloses a cloud layer detection and classification method based on multi-cloud-layer features, and the method comprises the steps: calculating the color, texture and shape feature quantities of a cloud picture, and building a cloud picture feature space; carrying out cloud layer pixel and sky pixel division on the shot current cloud picture by utilizing the optimal normalized red-blue ratio threshold value, and searching an optimal segmentation threshold value position on the normalized red-blue ratio histogram by adopting a minimum cross entropy method; and performing KNN classification on the currently photographed cloud picture according to the cloud picture feature space to obtain the type of the cloud layer to be shielded from the sun. According to the method, the cloud layer can be automatically and accurately detected based on the RGB characteristics of the cloud picture, the cloud layer characteristics are comprehensively extracted, and efficient and accurate judgment of the cloud layer type is achieved.

The invention belongs to the technical field of unmanned driving, and particularly relates to a method and device for detecting side rockfall of an unmanned vehicle. The method comprises the following steps: 1, obtaining the operation data of the unmanned vehicle in the driving process in real time, wherein the operation data comprises a driving speed and a driving angular speed, meanwhile, recording the road width in the driving process of the unmanned vehicle and the vehicle body width of the unmanned vehicle; 2, based on the operation data, the road width and the vehicle body width, defining a safety area and two monitoring areas on the two sides of a vehicle body, wherein the safety area is a safety area in the forward moving process of the vehicle, and the two monitoring areas are a first monitoring area located on the right side of the vehicle body and a second monitoring area located on the left side of the vehicle body. The method and device has the advantages of high intelligent degree, high safety and high accuracy.

The invention discloses a power distribution network operation data abnormity determination method based on data mining, and the method comprises the steps: setting original power grid operation data D and the number m of outliers, and putting the standardized data into a K-means + + clustering model; after the result of the clustering model is obtained, counting the data number n (i) of each cluster after clustering, and judging whether the value of i is greater than the set number m of outliers; if n (i) is greater than or equal to m, calculating LOF outlier factors of all objects of the class by adopting an LOF algorithm; a final outlier candidate set is generated, outlier factors of all data points are calculated and sorted, and a line loss abnormal condition set is formed; and carrying out inductive reasoning on the operation data in the line loss abnormal condition set to obtain abnormal occurrence time, tracing the abnormal occurrence time to a power distribution network structure, and positioning an abnormal occurrence place. According to the method, the occurrence of the abnormality in the operation data of the power distribution network can be efficiently and accurately judged, and the abnormality occurrence time and place are determined.

The invention discloses a method for identifying wheat scab resistance. The method comprises the following steps: inoculating wheat spike base internodes with a gibberella spore liquid after wheat heading, recording the browning condition of an inoculation point, judging whether the inoculation succeeds or not, respectively counting the scab rate on the 7th day, the 14th day and the 21st day afterthe inoculation, and dynamically evaluating the wheat scab resistance. The method has the greatest advantages of fastness and accuracy in observation of the disease condition and identification of the variety resistance, and solves the problems of difficult control of the spore inoculation amount, slow disease incidence, large simultaneous inoculation of the same variety in spike rate difference,high stem corrosion possibility and identification reliability influence of a stem injection method. Compared with the ear base stalk injection method, the method of the invention has the advantagesof consistent and small dosage of the spore liquid at the inoculation part, improvement of the consistency of disease attack, high inoculation efficiency, low cost, obvious phenotypic difference between variety resistance and variety susceptibility, and facilitation of common technicians can judge the gibberella disease resistance of wheat varieties.

The invention belongs to the related technical field of industrial robot milling systems, and particularly discloses a robot multi-axis milling stability model and a construction method thereof. The method specifically comprises the steps: establishing a local tool coordinate system in a robot multi-axis milling process, and determining a cutting contact area of an annular cutter through characteristic lines, intersecting lines and projection lines; deducing a dynamic milling force of multi-axis milling of the annular cutter, and establishing a multi-axis milling stability model under a local cutter coordinate system according to the dynamic milling force; and transforming the multi-axis milling stability model under the local tool coordinate system into the multi-axis milling stability model under the robot main shaft coordinate system through coordinate transformation. According to the method, the problem that the tool nose frequency response and the multi-axis milling force coordinate of a robot milling system are not unified is considered, the transformation relation between a tool coordinate system and a main shaft coordinate system is researched, and a multi-axis milling stability model under a local tool coordinate system is transformed into a robot main shaft coordinate system; and thus, a multi-axis milling stability model considering the redundant angle and the feeding direction of the robot is obtained.

The invention discloses a computer vision technology-based red tide real-time monitoring method. Through an interactive segmentation algorithm (a GrabCut algorithm) for extracting a foreground targetfrom a complex background, and by utilizing color space conversion, the influence of light ray conversion, water surface reflection and water surface floating objects in a monitored water area image can be resisted; a water surface foreground image can be efficiently and accurately obtained; the occurrence of a red tide can be accurately and quickly judged and an alarm is timely given; the cyclesof manual observation and sampling detection are greatly shortened; the limitations of a conventional detection method in personnel, time and space are broken through; related departments are facilitated to quickly adopt control measures; and large-area flooding of the red tide is avoided.

The invention provides a Bluetooth technology based automobile high beam and low beam automatic control system and belongs to the technical field of automobile lamps. Through the Bluetooth technology based automobile high beam and low beam automatic control system, the problem of how to accurately and efficiently realize automatic switching on a high beam and a low beam in the automobile driving process is solved. The automatic control system comprises a light intensity detection circuit, a Bluetooth transmission module, a single-chip microcomputer control circuit and a high-power constant current driving circuit which are connected in sequence. The single-chip microcomputer control circuit makes a judgment according to a detected cab light intensity signal of the Bluetooth transmission module, controls the high-power constant current driving circuit to operate to drive a load to conduct lighting when the ambient light is less than a set value, judges the condition of automobile meeting according to the light intensity change rate when high beams are turned on, gives a load high beam and low beam switching flickering prompt when it is judged that the high beams of an opposite automobile are turned on and controls the high beams to be switched to low beams after the prompt. The Bluetooth technology based automobile high beam and low beam automatic control system can efficiently and accurately judge the ambient light intensity and accurately and efficiently control the high beams and the low beams to be automatically switched to conform to the driving environment according to the ambient light change of a cab.

The invention relates to a real-time prediction method for rockburst in non-contact tunnel engineering construction. The real-time prediction method includes the steps of setting up a database, supplementing the database in site, establishing a monitoring system, adjusting a monitoring method in the working process and the like. The real-time prediction method has the effect that rockburst can bepredicted more precisely and quickly.

A status monitoring apparatus includes information obtaining means to obtain detected information items that are continuously detected; image data generating means to partition the detected information items by frames at predetermined time intervals, and configured to generate, for each frame, two-dimensional image data representing a distribution of detected information items in the frame, with an axis of abscissa being a time axis and an axis of ordinate being an axis showing a value/amount of the detected information items; and status detecting means to perform a machine learning based on the two-dimensional image data generated by the image data generating means to generate a correct label for judging whether the two-dimensional image data show at least a warning sign of failure, and to judge that at least a warning sign of failure has occurred in the detected information items, when the two-dimensional image data corresponding to the correct label are generated.

The invention discloses a comprehensive window integrated terminal which comprises an operation platform, a living card reader, a two-in-one card reader and a driving management card reader are embedded in the top of the operation platform, and one side of the driving management card reader is rotatably connected with a high-speed photographic apparatus. In summer, due to the fact that the weather is too dry, fingerprints cannot be collected on the identity card fingerprint instrument, water in the operation platform is heated through the electric heating element, generated steam is discharged through the steam holes, the fingers are wetted through the steam at the moment, then the fingerprints are collected, and more convenience and high efficiency are achieved; and meanwhile, through the arrangement of the V-shaped plate, on one hand, a channel is conveniently formed, steam is discharged, and on the other hand, cooled steam water drops can conveniently flow back into water, and inconvenience caused by overflowing of the cooled steam water drops is avoided.

The invention relates to a method for screening membrane protein interacting protein based on a yeast two-hybrid technology. Through the steps of bait protein carrier selection, self-activation detection, bait carrier function verification, membrane system two-hybrid library screening yeast, plasmid extraction, yeast plasmid propagation and the like, the selection of bait carriers is optimized, and by selecting suitable bait carriers, more interacting proteins can be screened to the maximum extent; the preparation process of yeast competent cells is optimized, the bacterium shaking process iswell grasped by a method close to certain quantity, thus the state of the yeast competent cells is optimized, the expression of a library is facilitated, the experiment progress can be well grasped, and the experiment stability is improved; and according to the final PCR verification of the membrane protein interaction based on an ubiquitin system, the efficiency and stability of a membrane protein interaction research method are greatly improved, and advanced technical means and theoretical basis are provided for science researchers.